Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4751 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.8544. Min Act: -0.0000

Data Index: 173213 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.5770. Min Act: -0.0000

Data Index: 894191 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.5023. Min Act: -0.0000

Data Index: 1070204 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.4859. Min Act: -0.0000

Data Index: 1030993 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.3613. Min Act: -0.0000

Data Index: 160315 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.4183. Min Act: -0.0000

Data Index: 939696 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.4080. Min Act: -0.0000

Data Index: 1017946 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.2442. Min Act: -0.0000

Data Index: 1025171 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.3203. Min Act: -0.0000

Data Index: 903020 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.2573. Min Act: -0.0000

Data Index: 827451 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1003542 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.2145. Min Act: -0.0000

Data Index: 255762 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.2824. Min Act: -0.0000

Data Index: 1304612 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.2660. Min Act: -0.0000

Data Index: 1211466 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.1254. Min Act: -0.0000

Data Index: 377348 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.1091. Min Act: -0.0000

Data Index: 612052 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.1936. Min Act: -0.0000

Data Index: 428428 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.1597. Min Act: -0.0000

Data Index: 270468 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1340318 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 1.8544. Min Range: -1.8544

Max Act: 1.3035. Min Act: -0.0000

Data Index: 402747 (C4 (Web Text))

Max Activating Token Index: 287